AI Paper Atlas

Research map / Continual learning / Class-incremental

Incremental Learning Using Conditional Adversarial Networks

Ye Xiang, Ying Fu, Pan Ji, Hua Huang

ICCV 2019 · Continual learning › Class-incremental · approach: Class-balanced knowledge retention · 190 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add adversarial loss (ablation)Ours · CIFAR-100 (incremental step 10)alpha_all: 0.654 -> 0.671Improved
add adversarial loss (ablation)Ours · CIFAR-100 (incremental step 10)alpha_orig: 0.623 -> 0.644Improved
add reconstruction loss (ablation)Ours · CIFAR-100 (incremental step 10)alpha_all: 0.663 -> 0.671Improved
add reconstruction loss (ablation)Ours · CIFAR-100 (incremental step 10)alpha_orig: 0.635 -> 0.644Improved
add adversarial and reconstruction losses to classification loss (ablation)Ours · CIFAR-100 (incremental step 10)alpha_all: 0.628 -> 0.671Improved
add adversarial and reconstruction losses to classification loss (ablation)Ours · CIFAR-100 (incremental step 10)alpha_orig: 0.597 -> 0.644Improved
add adversarial and reconstruction losses to classification loss (ablation)Ours · CIFAR-100 (incremental step 10)alpha_new: 0.842 -> 0.830Hurt
remove adversarial loss effect on new-class accuracy (ablation)Ours · CIFAR-100 (incremental step 10)alpha_new: 0.838 -> 0.830No clear effect
store statistics (s-way) instead of directly storing embeddings (d-way) (ablation)Ours · CIFAR-100 (step 10, t=5)alpha_all: 0.590 -> 0.591No clear effect
fine-tune convolutional layers too (Ours vs Ours-R)Ours · CIFAR-100 (incremental step 10)alpha_all: 0.625 -> 0.671Improved
fine-tune convolutional layers too (Ours vs Ours-R)Ours · CUB-200 (incremental step 10)alpha_all: 0.520 -> 0.576Improved
use conditional adversarial generator replay instead of FearNetOurs · CIFAR-100 (incremental step 25)alpha_all: 0.663 -> 0.670Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy